INDEX

Explanations

words written in a specific script or language, particularly focusing on phrases related to cultural or literary significance

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

γκ

-0.43

μα

-0.41

τρα

-0.39

μέ

-0.39

τ

-0.38

θ

-0.37

γ

-0.37

στα

-0.37

λα

-0.36

σ

-0.36

POSITIVE LOGITS

ಲು

0.80

ಾ

0.76

ಿಸ

0.75

ೋ

0.74

ಿದೆ

0.74

ೆ

0.73

್

0.73

ಚ

0.73

ಿ

0.72

ರ್

0.72

Activations Density 1.835%

words written in a specific script or language, particularly focusing on phrases related to cultural or literary significance

No Comments

No Known Activations